linux_dsm_epyc7002/include/linux/mutex.h

224 lines
6.6 KiB
C
Raw Normal View History

/*
* Mutexes: blocking mutual exclusion locks
*
* started by Ingo Molnar:
*
* Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*
* This file contains the main data structure and API definitions.
*/
#ifndef __LINUX_MUTEX_H
#define __LINUX_MUTEX_H
#include <asm/current.h>
#include <linux/list.h>
#include <linux/spinlock_types.h>
#include <linux/linkage.h>
#include <linux/lockdep.h>
#include <linux/atomic.h>
#include <asm/processor.h>
locking/spinlocks/mcs: Convert osq lock to atomic_t to reduce overhead The cancellable MCS spinlock is currently used to queue threads that are doing optimistic spinning. It uses per-cpu nodes, where a thread obtaining the lock would access and queue the local node corresponding to the CPU that it's running on. Currently, the cancellable MCS lock is implemented by using pointers to these nodes. In this patch, instead of operating on pointers to the per-cpu nodes, we store the CPU numbers in which the per-cpu nodes correspond to in atomic_t. A similar concept is used with the qspinlock. By operating on the CPU # of the nodes using atomic_t instead of pointers to those nodes, this can reduce the overhead of the cancellable MCS spinlock by 32 bits (on 64 bit systems). Signed-off-by: Jason Low <jason.low2@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Scott Norton <scott.norton@hp.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Waiman Long <waiman.long@hp.com> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Aswin Chandramouleeswaran <aswin@hp.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Chris Mason <clm@fb.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Josef Bacik <jbacik@fusionio.com> Link: http://lkml.kernel.org/r/1405358872-3732-3-git-send-email-jason.low2@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-15 00:27:49 +07:00
#include <linux/osq_lock.h>
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
#include <linux/debug_locks.h>
/*
* Simple, straightforward mutexes with strict semantics:
*
* - only one task can hold the mutex at a time
* - only the owner can unlock the mutex
* - multiple unlocks are not permitted
* - recursive locking is not permitted
* - a mutex object must be initialized via the API
* - a mutex object must not be initialized via memset or copying
* - task may not exit with mutex held
* - memory areas where held locks reside must not be freed
* - held mutexes must not be reinitialized
* - mutexes may not be used in hardware or software interrupt
* contexts such as tasklets and timers
*
* These semantics are fully enforced when DEBUG_MUTEXES is
* enabled. Furthermore, besides enforcing the above rules, the mutex
* debugging code also implements a number of additional features
* that make lock debugging easier and faster:
*
* - uses symbolic names of mutexes, whenever they are printed in debug output
* - point-of-acquire tracking, symbolic lookup of function names
* - list of all locks held in the system, printout of them
* - owner tracking
* - detects self-recursing locks and prints out all relevant info
* - detects multi-task circular deadlocks and prints out all affected
* locks and tasks (and only those tasks)
*/
struct mutex {
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
atomic_long_t owner;
spinlock_t wait_lock;
mutex: Queue mutex spinners with MCS lock to reduce cacheline contention The current mutex spinning code (with MUTEX_SPIN_ON_OWNER option turned on) allow multiple tasks to spin on a single mutex concurrently. A potential problem with the current approach is that when the mutex becomes available, all the spinning tasks will try to acquire the mutex more or less simultaneously. As a result, there will be a lot of cacheline bouncing especially on systems with a large number of CPUs. This patch tries to reduce this kind of contention by putting the mutex spinners into a queue so that only the first one in the queue will try to acquire the mutex. This will reduce contention and allow all the tasks to move forward faster. The queuing of mutex spinners is done using an MCS lock based implementation which will further reduce contention on the mutex cacheline than a similar ticket spinlock based implementation. This patch will add a new field into the mutex data structure for holding the MCS lock. This expands the mutex size by 8 bytes for 64-bit system and 4 bytes for 32-bit system. This overhead will be avoid if the MUTEX_SPIN_ON_OWNER option is turned off. The following table shows the jobs per minute (JPM) scalability data on an 8-node 80-core Westmere box with a 3.7.10 kernel. The numactl command is used to restrict the running of the fserver workloads to 1/2/4/8 nodes with hyperthreading off. +-----------------+-----------+-----------+-------------+----------+ | Configuration | Mean JPM | Mean JPM | Mean JPM | % Change | | | w/o patch | patch 1 | patches 1&2 | 1->1&2 | +-----------------+------------------------------------------------+ | | User Range 1100 - 2000 | +-----------------+------------------------------------------------+ | 8 nodes, HT off | 227972 | 227237 | 305043 | +34.2% | | 4 nodes, HT off | 393503 | 381558 | 394650 | +3.4% | | 2 nodes, HT off | 334957 | 325240 | 338853 | +4.2% | | 1 node , HT off | 198141 | 197972 | 198075 | +0.1% | +-----------------+------------------------------------------------+ | | User Range 200 - 1000 | +-----------------+------------------------------------------------+ | 8 nodes, HT off | 282325 | 312870 | 332185 | +6.2% | | 4 nodes, HT off | 390698 | 378279 | 393419 | +4.0% | | 2 nodes, HT off | 336986 | 326543 | 340260 | +4.2% | | 1 node , HT off | 197588 | 197622 | 197582 | 0.0% | +-----------------+-----------+-----------+-------------+----------+ At low user range 10-100, the JPM differences were within +/-1%. So they are not that interesting. The fserver workload uses mutex spinning extensively. With just the mutex change in the first patch, there is no noticeable change in performance. Rather, there is a slight drop in performance. This mutex spinning patch more than recovers the lost performance and show a significant increase of +30% at high user load with the full 8 nodes. Similar improvements were also seen in a 3.8 kernel. The table below shows the %time spent by different kernel functions as reported by perf when running the fserver workload at 1500 users with all 8 nodes. +-----------------------+-----------+---------+-------------+ | Function | % time | % time | % time | | | w/o patch | patch 1 | patches 1&2 | +-----------------------+-----------+---------+-------------+ | __read_lock_failed | 34.96% | 34.91% | 29.14% | | __write_lock_failed | 10.14% | 10.68% | 7.51% | | mutex_spin_on_owner | 3.62% | 3.42% | 2.33% | | mspin_lock | N/A | N/A | 9.90% | | __mutex_lock_slowpath | 1.46% | 0.81% | 0.14% | | _raw_spin_lock | 2.25% | 2.50% | 1.10% | +-----------------------+-----------+---------+-------------+ The fserver workload for an 8-node system is dominated by the contention in the read/write lock. Mutex contention also plays a role. With the first patch only, mutex contention is down (as shown by the __mutex_lock_slowpath figure) which help a little bit. We saw only a few percents improvement with that. By applying patch 2 as well, the single mutex_spin_on_owner figure is now split out into an additional mspin_lock figure. The time increases from 3.42% to 11.23%. It shows a great reduction in contention among the spinners leading to a 30% improvement. The time ratio 9.9/2.33=4.3 indicates that there are on average 4+ spinners waiting in the spin_lock loop for each spinner in the mutex_spin_on_owner loop. Contention in other locking functions also go down by quite a lot. The table below shows the performance change of both patches 1 & 2 over patch 1 alone in other AIM7 workloads (at 8 nodes, hyperthreading off). +--------------+---------------+----------------+-----------------+ | Workload | mean % change | mean % change | mean % change | | | 10-100 users | 200-1000 users | 1100-2000 users | +--------------+---------------+----------------+-----------------+ | alltests | 0.0% | -0.8% | +0.6% | | five_sec | -0.3% | +0.8% | +0.8% | | high_systime | +0.4% | +2.4% | +2.1% | | new_fserver | +0.1% | +14.1% | +34.2% | | shared | -0.5% | -0.3% | -0.4% | | short | -1.7% | -9.8% | -8.3% | +--------------+---------------+----------------+-----------------+ The short workload is the only one that shows a decline in performance probably due to the spinner locking and queuing overhead. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Reviewed-by: Davidlohr Bueso <davidlohr.bueso@hp.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Chandramouleeswaran Aswin <aswin@hp.com> Cc: Norton Scott J <scott.norton@hp.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: David Howells <dhowells@redhat.com> Cc: Dave Jones <davej@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1366226594-5506-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-18 02:23:13 +07:00
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
locking/spinlocks/mcs: Convert osq lock to atomic_t to reduce overhead The cancellable MCS spinlock is currently used to queue threads that are doing optimistic spinning. It uses per-cpu nodes, where a thread obtaining the lock would access and queue the local node corresponding to the CPU that it's running on. Currently, the cancellable MCS lock is implemented by using pointers to these nodes. In this patch, instead of operating on pointers to the per-cpu nodes, we store the CPU numbers in which the per-cpu nodes correspond to in atomic_t. A similar concept is used with the qspinlock. By operating on the CPU # of the nodes using atomic_t instead of pointers to those nodes, this can reduce the overhead of the cancellable MCS spinlock by 32 bits (on 64 bit systems). Signed-off-by: Jason Low <jason.low2@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Scott Norton <scott.norton@hp.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Waiman Long <waiman.long@hp.com> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Aswin Chandramouleeswaran <aswin@hp.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Chris Mason <clm@fb.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Josef Bacik <jbacik@fusionio.com> Link: http://lkml.kernel.org/r/1405358872-3732-3-git-send-email-jason.low2@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-15 00:27:49 +07:00
struct optimistic_spin_queue osq; /* Spinner MCS lock */
mutex: Queue mutex spinners with MCS lock to reduce cacheline contention The current mutex spinning code (with MUTEX_SPIN_ON_OWNER option turned on) allow multiple tasks to spin on a single mutex concurrently. A potential problem with the current approach is that when the mutex becomes available, all the spinning tasks will try to acquire the mutex more or less simultaneously. As a result, there will be a lot of cacheline bouncing especially on systems with a large number of CPUs. This patch tries to reduce this kind of contention by putting the mutex spinners into a queue so that only the first one in the queue will try to acquire the mutex. This will reduce contention and allow all the tasks to move forward faster. The queuing of mutex spinners is done using an MCS lock based implementation which will further reduce contention on the mutex cacheline than a similar ticket spinlock based implementation. This patch will add a new field into the mutex data structure for holding the MCS lock. This expands the mutex size by 8 bytes for 64-bit system and 4 bytes for 32-bit system. This overhead will be avoid if the MUTEX_SPIN_ON_OWNER option is turned off. The following table shows the jobs per minute (JPM) scalability data on an 8-node 80-core Westmere box with a 3.7.10 kernel. The numactl command is used to restrict the running of the fserver workloads to 1/2/4/8 nodes with hyperthreading off. +-----------------+-----------+-----------+-------------+----------+ | Configuration | Mean JPM | Mean JPM | Mean JPM | % Change | | | w/o patch | patch 1 | patches 1&2 | 1->1&2 | +-----------------+------------------------------------------------+ | | User Range 1100 - 2000 | +-----------------+------------------------------------------------+ | 8 nodes, HT off | 227972 | 227237 | 305043 | +34.2% | | 4 nodes, HT off | 393503 | 381558 | 394650 | +3.4% | | 2 nodes, HT off | 334957 | 325240 | 338853 | +4.2% | | 1 node , HT off | 198141 | 197972 | 198075 | +0.1% | +-----------------+------------------------------------------------+ | | User Range 200 - 1000 | +-----------------+------------------------------------------------+ | 8 nodes, HT off | 282325 | 312870 | 332185 | +6.2% | | 4 nodes, HT off | 390698 | 378279 | 393419 | +4.0% | | 2 nodes, HT off | 336986 | 326543 | 340260 | +4.2% | | 1 node , HT off | 197588 | 197622 | 197582 | 0.0% | +-----------------+-----------+-----------+-------------+----------+ At low user range 10-100, the JPM differences were within +/-1%. So they are not that interesting. The fserver workload uses mutex spinning extensively. With just the mutex change in the first patch, there is no noticeable change in performance. Rather, there is a slight drop in performance. This mutex spinning patch more than recovers the lost performance and show a significant increase of +30% at high user load with the full 8 nodes. Similar improvements were also seen in a 3.8 kernel. The table below shows the %time spent by different kernel functions as reported by perf when running the fserver workload at 1500 users with all 8 nodes. +-----------------------+-----------+---------+-------------+ | Function | % time | % time | % time | | | w/o patch | patch 1 | patches 1&2 | +-----------------------+-----------+---------+-------------+ | __read_lock_failed | 34.96% | 34.91% | 29.14% | | __write_lock_failed | 10.14% | 10.68% | 7.51% | | mutex_spin_on_owner | 3.62% | 3.42% | 2.33% | | mspin_lock | N/A | N/A | 9.90% | | __mutex_lock_slowpath | 1.46% | 0.81% | 0.14% | | _raw_spin_lock | 2.25% | 2.50% | 1.10% | +-----------------------+-----------+---------+-------------+ The fserver workload for an 8-node system is dominated by the contention in the read/write lock. Mutex contention also plays a role. With the first patch only, mutex contention is down (as shown by the __mutex_lock_slowpath figure) which help a little bit. We saw only a few percents improvement with that. By applying patch 2 as well, the single mutex_spin_on_owner figure is now split out into an additional mspin_lock figure. The time increases from 3.42% to 11.23%. It shows a great reduction in contention among the spinners leading to a 30% improvement. The time ratio 9.9/2.33=4.3 indicates that there are on average 4+ spinners waiting in the spin_lock loop for each spinner in the mutex_spin_on_owner loop. Contention in other locking functions also go down by quite a lot. The table below shows the performance change of both patches 1 & 2 over patch 1 alone in other AIM7 workloads (at 8 nodes, hyperthreading off). +--------------+---------------+----------------+-----------------+ | Workload | mean % change | mean % change | mean % change | | | 10-100 users | 200-1000 users | 1100-2000 users | +--------------+---------------+----------------+-----------------+ | alltests | 0.0% | -0.8% | +0.6% | | five_sec | -0.3% | +0.8% | +0.8% | | high_systime | +0.4% | +2.4% | +2.1% | | new_fserver | +0.1% | +14.1% | +34.2% | | shared | -0.5% | -0.3% | -0.4% | | short | -1.7% | -9.8% | -8.3% | +--------------+---------------+----------------+-----------------+ The short workload is the only one that shows a decline in performance probably due to the spinner locking and queuing overhead. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Reviewed-by: Davidlohr Bueso <davidlohr.bueso@hp.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Chandramouleeswaran Aswin <aswin@hp.com> Cc: Norton Scott J <scott.norton@hp.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: David Howells <dhowells@redhat.com> Cc: Dave Jones <davej@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1366226594-5506-4-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-04-18 02:23:13 +07:00
#endif
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
struct list_head wait_list;
mutex: implement adaptive spinning Change mutex contention behaviour such that it will sometimes busy wait on acquisition - moving its behaviour closer to that of spinlocks. This concept got ported to mainline from the -rt tree, where it was originally implemented for rtmutexes by Steven Rostedt, based on work by Gregory Haskins. Testing with Ingo's test-mutex application (http://lkml.org/lkml/2006/1/8/50) gave a 345% boost for VFS scalability on my testbox: # ./test-mutex-shm V 16 10 | grep "^avg ops" avg ops/sec: 296604 # ./test-mutex-shm V 16 10 | grep "^avg ops" avg ops/sec: 85870 The key criteria for the busy wait is that the lock owner has to be running on a (different) cpu. The idea is that as long as the owner is running, there is a fair chance it'll release the lock soon, and thus we'll be better off spinning instead of blocking/scheduling. Since regular mutexes (as opposed to rtmutexes) do not atomically track the owner, we add the owner in a non-atomic fashion and deal with the races in the slowpath. Furthermore, to ease the testing of the performance impact of this new code, there is means to disable this behaviour runtime (without having to reboot the system), when scheduler debugging is enabled (CONFIG_SCHED_DEBUG=y), by issuing the following command: # echo NO_OWNER_SPIN > /debug/sched_features This command re-enables spinning again (this is also the default): # echo OWNER_SPIN > /debug/sched_features Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-12 20:01:47 +07:00
#ifdef CONFIG_DEBUG_MUTEXES
void *magic;
#endif
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map dep_map;
#endif
};
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
static inline struct task_struct *__mutex_owner(struct mutex *lock)
{
return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03);
}
/*
* This is the control structure for tasks blocked on mutex,
* which resides on the blocked task's kernel stack:
*/
struct mutex_waiter {
struct list_head list;
struct task_struct *task;
#ifdef CONFIG_DEBUG_MUTEXES
void *magic;
#endif
};
#ifdef CONFIG_DEBUG_MUTEXES
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
#define __DEBUG_MUTEX_INITIALIZER(lockname) \
, .magic = &lockname
extern void mutex_destroy(struct mutex *lock);
#else
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
# define __DEBUG_MUTEX_INITIALIZER(lockname)
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
static inline void mutex_destroy(struct mutex *lock) {}
#endif
/**
* mutex_init - initialize the mutex
* @mutex: the mutex to be initialized
*
* Initialize the mutex to unlocked state.
*
* It is not allowed to initialize an already locked mutex.
*/
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
#define mutex_init(mutex) \
do { \
static struct lock_class_key __key; \
\
__mutex_init((mutex), #mutex, &__key); \
} while (0)
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
, .dep_map = { .name = #lockname }
#else
# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
#endif
#define __MUTEX_INITIALIZER(lockname) \
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
{ .owner = ATOMIC_LONG_INIT(0) \
, .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
, .wait_list = LIST_HEAD_INIT(lockname.wait_list) \
__DEBUG_MUTEX_INITIALIZER(lockname) \
__DEP_MAP_MUTEX_INITIALIZER(lockname) }
#define DEFINE_MUTEX(mutexname) \
struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
extern void __mutex_init(struct mutex *lock, const char *name,
struct lock_class_key *key);
/**
* mutex_is_locked - is the mutex locked
* @lock: the mutex to be queried
*
* Returns 1 if the mutex is locked, 0 if unlocked.
*/
static inline int mutex_is_locked(struct mutex *lock)
{
locking/mutex: Rework mutex::owner The current mutex implementation has an atomic lock word and a non-atomic owner field. This disparity leads to a number of issues with the current mutex code as it means that we can have a locked mutex without an explicit owner (because the owner field has not been set, or already cleared). This leads to a number of weird corner cases, esp. between the optimistic spinning and debug code. Where the optimistic spinning code needs the owner field updated inside the lock region, the debug code is more relaxed because the whole lock is serialized by the wait_lock. Also, the spinning code itself has a few corner cases where we need to deal with a held lock without an owner field. Furthermore, it becomes even more of a problem when trying to fix starvation cases in the current code. We end up stacking special case on special case. To solve this rework the basic mutex implementation to be a single atomic word that contains the owner and uses the low bits for extra state. This matches how PI futexes and rt_mutex already work. By having the owner an integral part of the lock state a lot of the problems dissapear and we get a better option to deal with starvation cases, direct owner handoff. Changing the basic mutex does however invalidate all the arch specific mutex code; this patch leaves that unused in-place, a later patch will remove that. Tested-by: Jason Low <jason.low2@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-23 18:36:04 +07:00
/*
* XXX think about spin_is_locked
*/
return __mutex_owner(lock) != NULL;
}
/*
* See kernel/locking/mutex.c for detailed documentation of these APIs.
locking/Documentation: Move locking related docs into Documentation/locking/ Specifically: Documentation/locking/lockdep-design.txt Documentation/locking/lockstat.txt Documentation/locking/mutex-design.txt Documentation/locking/rt-mutex-design.txt Documentation/locking/rt-mutex.txt Documentation/locking/spinlocks.txt Documentation/locking/ww-mutex-design.txt Signed-off-by: Davidlohr Bueso <davidlohr@hp.com> Acked-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: jason.low2@hp.com Cc: aswin@hp.com Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Chris Mason <clm@fb.com> Cc: Dan Streetman <ddstreet@ieee.org> Cc: David Airlie <airlied@linux.ie> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: David S. Miller <davem@davemloft.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jason Low <jason.low2@hp.com> Cc: Josef Bacik <jbacik@fusionio.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Lubomir Rintel <lkundrak@v3.sk> Cc: Masanari Iida <standby24x7@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: fengguang.wu@intel.com Link: http://lkml.kernel.org/r/1406752916-3341-6-git-send-email-davidlohr@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-31 03:41:55 +07:00
* Also see Documentation/locking/mutex-design.txt.
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
unsigned int subclass);
extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
unsigned int subclass);
#define mutex_lock(lock) mutex_lock_nested(lock, 0)
#define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
#define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
#define mutex_lock_nest_lock(lock, nest_lock) \
do { \
typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \
_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \
} while (0)
#else
extern void mutex_lock(struct mutex *lock);
extern int __must_check mutex_lock_interruptible(struct mutex *lock);
extern int __must_check mutex_lock_killable(struct mutex *lock);
# define mutex_lock_nested(lock, subclass) mutex_lock(lock)
# define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
# define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
#endif
/*
* NOTE: mutex_trylock() follows the spin_trylock() convention,
* not the down_trylock() convention!
*
* Returns 1 if the mutex has been acquired successfully, and 0 on contention.
*/
extern int mutex_trylock(struct mutex *lock);
extern void mutex_unlock(struct mutex *lock);
extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
/*
* These values are chosen such that FAIL and SUCCESS match the
* values of the regular mutex_trylock().
*/
enum mutex_trylock_recursive_enum {
MUTEX_TRYLOCK_FAILED = 0,
MUTEX_TRYLOCK_SUCCESS = 1,
MUTEX_TRYLOCK_RECURSIVE,
};
/**
* mutex_trylock_recursive - trylock variant that allows recursive locking
* @lock: mutex to be locked
*
* This function should not be used, _ever_. It is purely for hysterical GEM
* raisins, and once those are gone this will be removed.
*
* Returns:
* MUTEX_TRYLOCK_FAILED - trylock failed,
* MUTEX_TRYLOCK_SUCCESS - lock acquired,
* MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
*/
static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
mutex_trylock_recursive(struct mutex *lock)
{
if (unlikely(__mutex_owner(lock) == current))
return MUTEX_TRYLOCK_RECURSIVE;
return mutex_trylock(lock);
}
#endif /* __LINUX_MUTEX_H */